相关论文: Training-Free Activation Sparsity in Large Languag…

The complexity of multiagent reinforcement learning (MARL) in multiagent systems increases exponentially with respect to the agent number. This scalability issue prevents MARL from being applied in large-scale multiagent systems. However,…

Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually…

Reinforcement learning (RL) is a promising approach for robotic manipulation, but it can suffer from low sample efficiency and requires extensive exploration of large state-action spaces. Recent methods leverage the commonsense knowledge…

Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…

Large language models (LLMs) deliver strong performance but are difficult to deploy due to high memory and compute costs. While pruning reduces these demands, most methods ignore activation sparsity observed at runtime. We reinterpret…

Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to…

Large Language Models (LLMs) have exhibited exceptional performance across a spectrum of natural language processing tasks. However, their substantial sizes pose considerable challenges, particularly in computational demands and inference…

Large Language Models (LLMs) have enabled remarkable progress in natural language processing, yet their high computational and memory demands pose challenges for deployment in resource-constrained environments. Although recent low-rank…

Developed to alleviate prohibitive labeling costs, active learning (AL) methods aim to reduce label complexity in supervised learning. While recent work has demonstrated the benefit of using AL in combination with large pre-trained language…

Although Speech Large Language Models have achieved notable progress, a substantial modality reasoning gap remains: their reasoning performance on speech inputs is markedly weaker than on text. This gap could be associated with…

While Large Language Models (LLMs) have exhibited remarkable emergent capabilities through extensive pre-training, they still face critical limitations in generalizing to specialized domains and handling diverse linguistic variations, known…

This paper presents a comprehensive analysis of neural activation patterns across six distinct large language model (LLM) architectures, examining their performance on twelve cognitive task categories. Through systematic measurement of…

Vision-Language-Action (VLA) models pretrained on large-scale multimodal datasets have emerged as powerful foundations for robotic perception and control. However, their massive scale, often billions of parameters, poses significant…

Sparse neural networks are becoming increasingly important as the field seeks to improve the performance of existing models by scaling them up, while simultaneously trying to reduce power consumption and computational footprint.…

Mixture-of-Experts (MoE) architectures enhance the efficiency of large language models by activating only a subset of experts per token. However, standard MoE employs a fixed Top-K routing strategy, leading to redundant computation and…

The demand for efficient large language model (LLM) inference has propelled the development of dedicated accelerators. As accelerators are vulnerable to hardware faults due to aging, variation, etc, existing accelerator designs often…

Test-Time Scaling (TTS) has proven effective in improving the performance of Large Language Models (LLMs) during inference. However, existing research has overlooked the efficiency of TTS from a latency-sensitive perspective. Through a…

We propose a new algorithm to learn the network of the interactions of pairwise Ising models. The algorithm is based on the pseudo-likelihood method (PLM), that has already been proven to efficiently solve the problem in a large variety of…

Continual Learning is an unresolved challenge, whose relevance increases when considering modern applications. Unlike the human brain, trained deep neural networks suffer from a phenomenon called catastrophic forgetting, wherein they…

Large Language Model (LLM) applications have emerged as a prominent use case for Function-as-a-Service (FaaS) due to their high computational demands and sporadic invocation patterns. However, serving LLM functions within FaaS frameworks…